MapReduce WordCount示例

依赖

 <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.2.0</version>
        </dependency>
    </dependencies>

代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;

public class MyMapReduce {

    public static class MyMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

        private  IntWritable one = new IntWritable(1);

        private Text word = new Text();

        public void map(LongWritable offset, Text value, Context context)
                throws IOException, InterruptedException {
            String[] split = value.toString().split(",");
            for (int i = 0; i < split.length; i++) {
                String wordString = split[i];
                word.set(wordString);
                context.write(word, one);
            }
        }
    }

    public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

        private IntWritable sum = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sumStage = 0;
            for (IntWritable value : values) {
               sumStage += value.get();
            }
            sum.set(sumStage);
            context.write(key, sum);
        }
    }


    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "MyMapperReduce");
        //设置reduce个数默认1
        job.setNumReduceTasks(1);
        //设置类
        job.setJarByClass(MyMapReduce.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);
        //设置输出类型如果mapper输出跟reduce类型相同可以不用设置
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //设置输入输出文件
        //C:\Users\xxx\Desktop\in.txt C:\Users\xxx\Desktop\out.txt
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        //job执行结束退出
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

报错信息:

Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z
	at org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Native Method)
	at org.apache.hadoop.io.nativeio.NativeIO$Windows.access(NativeIO.java:435)
	at org.apache.hadoop.fs.FileUtil.canRead(FileUtil.java:977)
	at org.apache.hadoop.util.DiskChecker.checkAccessByFileMethods(DiskChecker.java:177)
	at org.apache.hadoop.util.DiskChecker.checkDirAccess(DiskChecker.java:164)
	at org.apache.hadoop.util.DiskChecker.checkDir(DiskChecker.java:98)
	at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.confChanged(LocalDirAllocator.java:285)
	at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.getLocalPathForWrite(LocalDirAllocator.java:344)
	at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:150)
	at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:131)
	at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:115)
	at org.apache.hadoop.mapred.LocalDistributedCacheManager.setup(LocalDistributedCacheManager.java:131)
	at org.apache.hadoop.mapred.LocalJobRunner$Job.<init>(LocalJobRunner.java:157)
	at org.apache.hadoop.mapred.LocalJobRunner.submitJob(LocalJobRunner.java:636)
	at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:430)
	at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1268)
	at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1265)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1491)
	at org.apache.hadoop.mapreduce.Job.submit(Job.java:1265)
	at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1286)
	at com.anji.mr.MyMapReduce.main(MyMapReduce.java:67)

需要找对应hadoop版本的hadoop.dll(版本不对应可能还会报错)文件并放到对应目录下
如果百度搜不到就在github中搜索 hadoop-common-2.2.0-bin 查找,版本更换成自己的需要的版本号.

in.txt

运行成功后